From owner-freebsd-hardware@FreeBSD.ORG Wed Aug 4 20:48:57 2004 Return-Path: Delivered-To: freebsd-hardware@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B493416A4CE for ; Wed, 4 Aug 2004 20:48:57 +0000 (GMT) Received: from odin.ac.hmc.edu (Odin.AC.HMC.Edu [134.173.32.75]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8BE6643D2F for ; Wed, 4 Aug 2004 20:48:57 +0000 (GMT) (envelope-from brdavis@odin.ac.hmc.edu) Received: from odin.ac.hmc.edu (IDENT:brdavis@localhost.localdomain [127.0.0.1]) by odin.ac.hmc.edu (8.12.10/8.12.10) with ESMTP id i74KmrOF032745; Wed, 4 Aug 2004 13:48:53 -0700 Received: (from brdavis@localhost) by odin.ac.hmc.edu (8.12.10/8.12.3/Submit) id i74KmreV032744; Wed, 4 Aug 2004 13:48:53 -0700 Date: Wed, 4 Aug 2004 13:48:53 -0700 From: Brooks Davis To: Zoltan HERPAI Message-ID: <20040804204853.GE10063@Odin.AC.HMC.Edu> References: <4110C9C7.6080506@kaqelectronics.dyndns.org> <20040804164954.GB10063@Odin.AC.HMC.Edu> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Q8BnQc91gJZX4vDc" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.4i cc: kat-free@kaqelectronics.dyndns.org cc: freebsd-hardware@freebsd.org Subject: Re: Big Problem X-BeenThere: freebsd-hardware@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: General discussion of FreeBSD hardware List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 04 Aug 2004 20:48:57 -0000 --Q8BnQc91gJZX4vDc Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Aug 04, 2004 at 09:47:37PM +0200, Zoltan HERPAI wrote: > On Wed, 4 Aug 2004, Brooks Davis wrote: >=20 > > On Wed, Aug 04, 2004 at 07:34:31PM +0800, Kathy Quinlan wrote: > > > Design a computer (probably multiple AMD 64's) to handle 10TB of memo= ry > > > (+ a few extra Gb of ram for system overhead) and hold the file in one > > > physical computer system. > > You would do well to read up on the techniques used by google to manage > > unreliable systems and provide high-performance search. > what about the tandem non-stop systems? it'll cost a pile of bucks.. but, > i'm still unsure why a large cluster of oracle, or any specially designed > rdbms wouldn't do the job. By and large, I'm highly skeptical of "solutions" involving massives amounts of very expensive hardware especialy when you toss software with very expensive, per-cpu licenses. I'm sure you could do it this way, but given that 10TB of RAM will cost nearly $5M for commodity systems, I hate to think what it would cost for high end systems where it is sold at a 5-10x markup. -- Brooks --=20 Any statement of the form "X is the one, true Y" is FALSE. PGP fingerprint 655D 519C 26A7 82E7 2529 9BF0 5D8E 8BE9 F238 1AD4 --Q8BnQc91gJZX4vDc Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.1 (GNU/Linux) iD8DBQFBEUu0XY6L6fI4GtQRAmZNAJ47butC1aKZvA1rscD/tsv83SHL1QCg1Qyx HK2fpFpHuxnP70LpJH6///4= =nAEs -----END PGP SIGNATURE----- --Q8BnQc91gJZX4vDc--